A novel assessment of whole-mount Gleason grading in prostate
cancer to identify candidates for radical prostatectomy: a
machine learning-based multiomics

J 2024

A novel assessment of whole-mount Gleason grading in prostate cancer to identify candidates for radical prostatectomy: a machine learning-based multiomics

NING, Jing; Clemens P SPIELVOGEL; David HABERL; Karolína TRACHTOVÁ; Stefan STOIBER et. al.

Základní údaje

Originální název

A novel assessment of whole-mount Gleason grading in prostate cancer to identify candidates for radical prostatectomy: a machine learning-based multiomics

Autoři

Vydání

Theranostics, Lake Haven, Ivyspring International Publisher, 2024, 1838-7640

Další údaje

Jazyk

angličtina

Typ výsledku

Článek v odborném periodiku

Obor

30204 Oncology

Stát vydavatele

Austrálie

Utajení

není předmětem státního či obchodního tajemství

Odkazy

URL

Impakt faktor

Impact factor: 13.300

Kód RIV

RIV/00216224:14740/24:00138855

Organizační jednotka

Středoevropský technologický institut

DOI

https://doi.org/10.7150/thno.96921

UT WoS

001306645700002

EID Scopus

2-s2.0-85201507395

Klíčová slova anglicky

prostate cancer; PSMA; Gleason grading; machine learning; multiomics

Štítky

CF BIOIT, CF GEN, rivok

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 18. 3. 2025 12:40, Mgr. Eva Dubská

Anotace

V originále

Purpose: : This study aims to assess whole-mount Gleason grading (GG) in prostate cancer (PCa) accurately using a multiomics machine learning (ML) model and to compare its performance with biopsy-proven GG (bxGG) assessment. Materials and Methods: : A total of 146 patients with PCa recruited in a pilot study of a prospective clinical trial (NCT02659527) were retrospectively included in the side study, all of whom underwent 68 Ga-PSMA-11 integrated positron emission tomography (PET) / magnetic resonance (MR) before radical prostatectomy (RP) between May 2014 and April 2020. To establish a multiomics ML model, we quantified PET radiomics features, pathway-level genomics features from whole exome sequencing, and pathomics features derived from immunohistochemical staining of 11 biomarkers. Based on the multiomics dataset, five ML models were established and validated using 100-fold Monte Carlo cross-validation. Results: : Among five ML models, the random forest (RF) model performed best in terms of the area under the curve (AUC). Compared to bxGG assessment alone, the RF model was superior in terms of AUC (0.87 vs 0.75), specificity (0.72 vs 0.61), positive predictive value (0.79 vs 0.75), and accuracy (0.78 vs 0.77) and showed slightly decreased sensitivity (0.83 vs 0.89) and negative predictive value (0.80 vs 0.81). Among the feature categories, bxGG was identified as the most important feature, followed by pathomics, clinical, radiomics and genomics features. The three important individual features were bxGG, PSA staining and one intensity-related radiomics feature. Conclusion: : The findings demonstrate a superior assessment of the developed multiomics-based ML model in whole-mount GG compared to the current clinical baseline of bxGG. This enables personalized patient management by identifying high-risk PCa patients for RP.

Návaznosti

90267, velká výzkumná infrastruktura

Název: NCMG III

Citovat

NING, Jing; Clemens P SPIELVOGEL; David HABERL; Karolína TRACHTOVÁ; Stefan STOIBER; Sazan RASUL; Vojtěch BYSTRÝ; Gabriel WASINGER; Pascal BALTZER; Elisabeth GURNHOFER; Gerald TIMELTHALER; Michaela SCHLEDERER; Laszlo PAPP; Helga SCHACHNER; Thomas HELBICH; Markus HARTENBACH; Bernhard GRUBMUELLER; Shahrokh F SHARIAT; Marcus HACKER; Alexander HAUG a Lukas KENNER. A novel assessment of whole-mount Gleason grading in prostate cancer to identify candidates for radical prostatectomy: a machine learning-based multiomics. Theranostics. Lake Haven: Ivyspring International Publisher, 2024, roč. 14, č. 12, s. 4570-4581. ISSN 1838-7640. Dostupné z: https://doi.org/10.7150/thno.96921.

@article{2476920,
   author = {Ning, Jing and Spielvogel, Clemens P and Haberl, David and Trachtová, Karolína and Stoiber, Stefan and Rasul, Sazan and Bystrý, Vojtěch and Wasinger, Gabriel and Baltzer, Pascal and Gurnhofer, Elisabeth and Timelthaler, Gerald and Schlederer, Michaela and Papp, Laszlo and Schachner, Helga and Helbich, Thomas and Hartenbach, Markus and Grubmueller, Bernhard and Shariat, Shahrokh F and Hacker, Marcus and Haug, Alexander and Kenner, Lukas},
   article_location = {Lake Haven},
   article_number = {12},
   doi = {https://doi.org/10.7150/thno.96921},
   keywords = {prostate cancer; PSMA; Gleason grading; machine learning; multiomics},
   language = {eng},
   issn = {1838-7640},
   journal = {Theranostics},
   title = {A novel assessment of whole-mount Gleason grading in prostate cancer to identify candidates for radical prostatectomy: a machine learning-based multiomics},
   url = {https://www.thno.org/v14p4570.htm},
   volume = {14},
   year = {2024}
}

TY  - JOUR
ID  - 2476920
AU  - Ning, Jing - Spielvogel, Clemens P - Haberl, David - Trachtová, Karolína - Stoiber, Stefan - Rasul, Sazan - Bystrý, Vojtěch - Wasinger, Gabriel - Baltzer, Pascal - Gurnhofer, Elisabeth - Timelthaler, Gerald - Schlederer, Michaela - Papp, Laszlo - Schachner, Helga - Helbich, Thomas - Hartenbach, Markus - Grubmueller, Bernhard - Shariat, Shahrokh F - Hacker, Marcus - Haug, Alexander - Kenner, Lukas
PY  - 2024
TI  - A novel assessment of whole-mount Gleason grading in prostate cancer to identify candidates for radical prostatectomy: a machine learning-based multiomics
JF  - Theranostics
VL  - 14
IS  - 12
SP  - 4570-4581
EP  - 4570-4581
PB  - Ivyspring International Publisher
SN  - 18387640
KW  - prostate cancer
KW  - PSMA
KW  - Gleason grading
KW  - machine learning
KW  - multiomics
UR  - https://www.thno.org/v14p4570.htm
N2  - Purpose: : This study aims to assess whole-mount Gleason grading (GG) in prostate cancer (PCa) accurately using a multiomics machine learning (ML) model and to compare its performance with biopsy-proven GG (bxGG) assessment. Materials and Methods: : A total of 146 patients with PCa recruited in a pilot study of a prospective clinical trial (NCT02659527) were retrospectively included in the side study, all of whom underwent 68 Ga-PSMA-11 integrated positron emission tomography (PET) / magnetic resonance (MR) before radical prostatectomy (RP) between May 2014 and April 2020. To establish a multiomics ML model, we quantified PET radiomics features, pathway-level genomics features from whole exome sequencing, and pathomics features derived from immunohistochemical staining of 11 biomarkers. Based on the multiomics dataset, five ML models were established and validated using 100-fold Monte Carlo cross-validation. Results: : Among five ML models, the random forest (RF) model performed best in terms of the area under the curve (AUC). Compared to bxGG assessment alone, the RF model was superior in terms of AUC (0.87 vs 0.75), specificity (0.72 vs 0.61), positive predictive value (0.79 vs 0.75), and accuracy (0.78 vs 0.77) and showed slightly decreased sensitivity (0.83 vs 0.89) and negative predictive value (0.80 vs 0.81). Among the feature categories, bxGG was identified as the most important feature, followed by pathomics, clinical, radiomics and genomics features. The three important individual features were bxGG, PSA staining and one intensity-related radiomics feature. Conclusion: : The findings demonstrate a superior assessment of the developed multiomics-based ML model in whole-mount GG compared to the current clinical baseline of bxGG. This enables personalized patient management by identifying high-risk PCa patients for RP.
ER  -

NING, Jing; Clemens P SPIELVOGEL; David HABERL; Karolína TRACHTOVÁ; Stefan STOIBER; Sazan RASUL; Vojtěch BYSTRÝ; Gabriel WASINGER; Pascal BALTZER; Elisabeth GURNHOFER; Gerald TIMELTHALER; Michaela SCHLEDERER; Laszlo PAPP; Helga SCHACHNER; Thomas HELBICH; Markus HARTENBACH; Bernhard GRUBMUELLER; Shahrokh F SHARIAT; Marcus HACKER; Alexander HAUG a Lukas KENNER. A novel assessment of whole-mount Gleason grading in prostate cancer to identify candidates for radical prostatectomy: a machine learning-based multiomics. \textit{Theranostics}. Lake Haven: Ivyspring International Publisher, 2024, roč.~14, č.~12, s.~4570-4581. ISSN~1838-7640. Dostupné z: https://doi.org/10.7150/thno.96921.

Přehled o publikaci